{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IFL7GS3QJXB3DCS7YMVCGYT5YT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12"},"schema_version":"1.0","source":{"id":"2112.07254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07254v1","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"IFL7GS3QJXB3","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"IFL7GS3QJXB3DCS7","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"IFL7GS3Q","created_at":"2026-07-05T03:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e","target":"graph","created_at":"2026-07-05T03:40:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.07254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the self-supervised pre-training methods because its decoder is conditioned on acoustic representation thus cannot be pretrained separately. In this paper, we propose a pretrained Transformer (Preformer) S2S ASR architecture based on hybrid CTC/attention E2E models to fully utilize the pretrained acoustic models (AMs) and language models (LMs). In our framework, the encoder is init","authors_text":"Keqi Deng, Long Ma, Songjun Cao, Yike Zhang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title":"Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07254","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b","target":"record","created_at":"2026-07-05T03:40:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12"},"schema_version":"1.0","source":{"id":"2112.07254","kind":"arxiv","version":1}},"canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","first_computed_at":"2026-07-05T03:40:56.376150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:56.376150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JL4vfoF0ZULbQZG3V/Kf7nu04LH+X9hcoi++8u0JjWA8QQP9USpxb1JMzY6Mh4hmWNmLwfGic41MKmWBVDN7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:56.376637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b","sha256:ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e"],"state_sha256":"ffa80ccf38c065c13c9c15fb681db19d6f9e94980431cafac55860583f2a1ac3"}